© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4756
    Prev
    Next
    INDEX
    Explanations

    programming-related references to preparation and execution of database queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    windowFixed
    -0.39
     mirador
    -0.33
     élus
    -0.32
    noStroke
    -0.32
     kysy
    -0.31
     comedor
    -0.30
     Corazón
    -0.30
    pyplot
    -0.30
     ungef
    -0.29
     löyty
    -0.29
    POSITIVE LOGITS
     preparation
    3.88
     prepare
    3.50
     Preparation
    3.42
    preparation
    3.34
     preparing
    3.33
     preparations
    3.30
     prepares
    3.22
     prepared
    3.19
    Preparation
    3.16
     prepar
    3.14
    Activations Density 0.734%

    No Known Activations